© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 4769
    Prev
    Next
    INDEX
    Explanations

    color-related words or color names

    oai_token-act-pair · gpt-3.5-turbo

    colors and names related to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reply
    -0.88
    natureconservancy
    -0.74
    ansas
    -0.72
    Fund
    -0.70
    JECT
    -0.70
    dig
    -0.68
    xy
    -0.67
    iley
    -0.66
    Network
    -0.65
     Podesta
    -0.63
    POSITIVE LOGITS
    ancies
    0.95
    ás
    0.94
    orescence
    0.90
    olson
    0.90
    otine
    0.89
    uate
    0.88
    hyde
    0.87
    osi
    0.83
    umn
    0.83
    uation
    0.82
    Activations Density 0.011%

    No Known Activations